© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 63394
    Prev
    Next
    INDEX
    Explanations

    Desktop pictures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ctx
    -0.08
     hita
    -0.07
     polymer
    -0.07
    ционной
    -0.07
    soa
    -0.07
     noct
    -0.07
    Cmp
    -0.07
    cstring
    -0.07
    -0.07
    pos
    -0.07
    POSITIVE LOGITS
     روپے
    0.08
     двери
    0.08
     Lovers
    0.08
    (letter
    0.08
     jogador
    0.08
     vooraf
    0.08
     YE
    0.08
     استاند
    0.08
     krás
    0.08
     MAIS
    0.08
    Activations Density 0.001%
    No Known Activations